update detection readme (#1063)

Signed-off-by: Can Zhao <[email protected]>

Fixes #1064 .

### Description
Update detection readme to add data download link and add note for dicom
data download.

### Checks
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [ ] Notebook runs automatically `./runner [-p <regex_pattern>]`

Signed-off-by: Can Zhao <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: Can-Zhao

detection/README.md

@@ -15,12 +15,10 @@ MONAI detection implementation is based on the following papers:
 
 ### 1. Data
 
-The dataset we are experimenting in this example is LUNA16 (https://luna16.grand-challenge.org/Home/), which is based on [LIDC/IDRI database](https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI) [1,2,3].
+The dataset we are experimenting in this example is LUNA16 (https://luna16.grand-challenge.org/Home/), which is based on [LIDC/IDRI database](https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=1966254) [1,2,3].
 
 LUNA16 is a public dataset of CT lung nodule detection. Using raw CT scans, the goal is to identify locations of possible nodules, and to assign a probability for being a nodule to each location.
 
-Users can either download mhd/raw data from [LUNA16](https://luna16.grand-challenge.org/Home/), or DICOM data from [LIDC-IDRI](https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=1966254).
-
 Disclaimer: We are not the host of the data. Please make sure to read the requirements and usage policies of the data and give credit to the authors of the dataset! We acknowledge the National Cancer Institute and the Foundation for the National Institutes of Health, and their critical role in the creation of the free publicly available LIDC/IDRI Database used in this study.
 
 We follow the official 10-fold data splitting from LUNA16 challenge and generate data split json files using the script from [nnDetection](https://github.com/MIC-DKFZ/nnDetection/blob/main/projects/Task016_Luna/scripts/prepare.py).
@@ -35,6 +33,10 @@ In these files, the values of "box" are the ground truth boxes in world coordina
 
 ### 3. Run the example
 #### [3.1 Prepare Your Data](./luna16_prepare_images.py)
+We provide [resampled Nifti images](https://drive.google.com/drive/folders/1JozrufA1VIZWJIc5A1EMV3J4CNCYovKK?usp=share_link) for users to download (recommended).
+If you do this, please skip Sec. 3.1 and go directly to Sec. 3.2.
+
+Alternatively, users can download the original data and resample them with the following steps. Users can either download 1) mhd/raw data from [LUNA16](https://luna16.grand-challenge.org/Home/) or its [copy](https://drive.google.com/drive/folders/1-enN4eNEnKmjltevKg3W2V-Aj0nriQWE?usp=share_link), or 2) DICOM data from [LIDC-IDRI](https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=1966254) with [NBIA Data Retriever](https://wiki.cancerimagingarchive.net/display/NBIA/Downloading+TCIA+Images).
 
 The raw CT images in LUNA16 have various of voxel sizes. The first step is to resample them to the same voxel size, which is defined in the value of "spacing" in [./config/config_train_luna16_16g.json](./config/config_train_luna16_16g.json).
 
@@ -51,9 +53,11 @@ If you downloaded DICOM data, please resample the images by running
 python3 luna16_prepare_env_files.py
 python3 luna16_prepare_images_dicom.py -c ./config/config_train_luna16_16g.json
 ```
+Note that for DICOM data, the data split json files are based on data downloaded with [NBIA Data Retriever](https://wiki.cancerimagingarchive.net/display/NBIA/Downloading+TCIA+Images).
 
 The resampled images will be with Nifti format.
 
+
 #### [3.2 3D Detection Training](./luna16_training.py)
 
 The LUNA16 dataset was splitted into 10-fold to run cross-fold training and inference.
@@ -96,7 +100,7 @@ python3 luna16_testing.py \
 
 #### [3.4 LUNA16 Detection Evaluation](./run_luna16_offical_eval.sh)
 Please download the official LUNA16 evaluation scripts from https://luna16.grand-challenge.org/Evaluation/,
-and save it as ./evaluation_luna16
+and save it as ./evaluation_luna16. Note that the official LUNA16 evaluation scripts are based on Python2.
 
 ./evaluation_luna16/noduleCADEvaluationLUNA16.py will be the main python script to generate evaluation scores.
 

detection/run_luna16_offical_eval.sh

@@ -25,7 +25,7 @@ python ./luna16_post_combine_cross_fold_results.py \
 	-o ./result/result_luna16_all.csv
 
 mkdir -p ./result/eval_luna16_scores
-python ./evaluation_luna16/noduleCADEvaluationLUNA16.py \
+python2 ./evaluation_luna16/noduleCADEvaluationLUNA16.py \
 	./evaluation_luna16/annotations/annotations.csv  \
 	./evaluation_luna16/annotations/annotations_excluded.csv \
 	./evaluation_luna16/annotations/seriesuids.csv \